- Rank
- #131
- Total Output Tokens
- 269,351
- Response Time (avg)
- 105.03s
- Total Cost
- $0.086
Gemma 4 26B A4B (medium) vs Inkling Small (high)
The average score is effectively tied at 7.3 vs 7.4. Gemma 4 26B A4B (medium) has the lower benchmark cost at $0.086 vs $0.402. Inkling Small (high) is faster at 29.10s vs 105.03s, with pass rates of 71.0% vs 66.7%.
Compared models
- Rank
- #128
- Total Output Tokens
- 298,893
- Response Time (avg)
- 29.10s
- Total Cost
- $0.402
Recommended model
Gemma 4 26B A4B (medium)
It has the best score here (7.3), while costing about 4.7x less than Inkling Small (high).
Detailed comparison
| Metric | Gemma 4 26B A4B Gemma 4 26B A4B medium Free Available | Inkling Small Inkling Small high Free Available |
|---|---|---|
| Score | 7.3 | 7.4 |
| Rank | #131 | #128 |
| Reliability | 10.0 | 10.0 |
| Consistency | 9.6 | 9.3 |
| Attempts | 69/69 | 69/69 |
| Tests Correct | ||
| Attempt pass rate | 71.0% | 66.7% |
| Flaky tests | 1 | 2 |
| Total Runs | 69 | 69 |
| Cost per result | 0.679 | 2.868 |
| Total Cost | $0.086 | $0.402 |
| Input Price | $0.077 / 1M | $0.450 / 1M |
| Output Price | $0.255 / 1M | $1.200 / 1M |
| Total Input Tokens | 224,367 | 85,669 |
| Output Tokens | 27,095 | 6,092 |
| Reasoning Tokens | 242,256 | 292,801 |
| Response Time (avg) | 105.03s | 29.10s |
| Response Time (max) | 912.19s | 122.60s |
| Response Time (total) | 2310.63s | 669.40s |
| Parameters | 25.2B total (3.8B active) | 276B total (12B active) |
| Availability | Open source | Closed |
Model generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#131 Gemma 4 26B A4B
medium
Reached the allocated time limit (300 seconds) without receiving showcase output.
- Cost
- $0.000
- Time
- 300.0s
- Tokens
- 0 tok
#128 Thinking Machines: Inkling Small
high- Cost
- $0.006
- Time
- 34.7s
- Tokens
- 4,735 tok
Top Models by Score
Score vs Total Cost
Response Time (avg)
Score vs Response Time (avg)
Total Output Tokens
Score vs Total Output Tokens
Category Breakdown
| Agentic | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemma 4 26B A4B | 10.0 | 10.0 | 100.0% | 0 | 107.12s | 146,839 | 1,047 | 14,658 | |
| Inkling Small | 3.0 | 10.0 | 0.0% | 0 | 23ms | 0 | 0 | 0 |
| Anti-AI Tricks | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemma 4 26B A4B | 10.0 | 10.0 | 100.0% | 0 | 6.20s | 816 | 1,142 | 3,045 | |
| Inkling Small | 10.0 | 10.0 | 100.0% | 0 | 6.30s | 702 | 335 | 9,678 |
| Coding | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemma 4 26B A4B | 2.9 | 10.0 | 0.0% | 0 | 272.54s | 5,062 | 14,838 | 44,567 | |
| Inkling Small | 10.0 | 10.0 | 100.0% | 0 | 93.23s | 7,374 | 463 | 120,474 |
| Combined | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemma 4 26B A4B | 6.3 | 10.0 | 50.0% | 0 | 492.87s | 54,390 | 5,451 | 132,113 | |
| Inkling Small | 9.9 | 10.0 | 100.0% | 0 | 40.41s | 61,630 | 4,001 | 28,812 |
| Data parsing and extraction | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemma 4 26B A4B | 10.0 | 10.0 | 100.0% | 0 | 16.51s | 8,334 | 1,567 | 2,827 | |
| Inkling Small | 10.0 | 10.0 | 100.0% | 0 | 3.99s | 7,068 | 216 | 2,763 |
| Domain specific | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemma 4 26B A4B | 5.3 | 7.2 | 44.4% | 1 | 35.14s | 494 | 481 | 15,212 | |
| Inkling Small | 5.3 | 10.0 | 33.3% | 0 | 56.28s | 804 | 69 | 84,578 |
| General Intelligence | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemma 4 26B A4B | 10.0 | 10.0 | 100.0% | 0 | 29.76s | 567 | 25 | 5,075 | |
| Inkling Small | 5.3 | 10.0 | 0.0% | 0 | 3.62s | 501 | 153 | 1,395 |
| Instructions following | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemma 4 26B A4B | 10.0 | 10.0 | 100.0% | 0 | 17.54s | 777 | 887 | 4,470 | |
| Inkling Small | 9.8 | 10.0 | 100.0% | 0 | 3.94s | 708 | 94 | 2,742 |
| Puzzle Solving | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemma 4 26B A4B | 10.0 | 10.0 | 100.0% | 0 | 5.79s | 801 | 410 | 2,128 | |
| Inkling Small | 4.8 | 4.4 | 44.5% | 2 | 14.39s | 714 | 482 | 18,286 |
| Tool Calling | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemma 4 26B A4B | 10.0 | 10.0 | 100.0% | 0 | 9.01s | 6,096 | 450 | 1,256 | |
| Inkling Small | 3.0 | 10.0 | 0.0% | 0 | 2.91s | 5,949 | 249 | 577 |
| Trivia | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemma 4 26B A4B | 3.0 | 10.0 | 0.0% | 0 | 180.87s | 191 | 797 | 16,905 | |
| Inkling Small | 3.0 | 10.0 | 0.0% | 0 | 49.27s | 219 | 30 | 23,496 |
Quick Compare
Switch Comparison Pair
Inkling SmallhighFree AvailablevsGrok 4.7lowSeed-2.0-CodemediumvsInkling SmallhighFree AvailableDeepSeek V4 Pro 0423nonevsInkling SmallhighFree AvailableGemma 4 26B A4BmediumFree AvailablevsGLM 5.3 FlashhighDeepSeek V4 Flash 0731lowvsInkling SmallhighFree AvailableDeepSeek V4 Pro 0423nonevsGemma 4 26B A4BmediumFree AvailableQwen3.6 FlashmediumvsInkling SmallhighFree AvailableGPT-5.6 LunamediumvsInkling SmallhighFree AvailableGemma 4 26B A4BmediumFree AvailablevsGrok 4.7lowGemma 4 26B A4BmediumFree AvailablevsGLM 5.3 FlashXhighGemma 4 26B A4BmediumFree AvailablevsLongCat 2.0highDeepSeek V4 Flash 0731lowvsGemma 4 26B A4BmediumFree Available